Advertisement

Combined orientation and skew detection using geometric text-line modeling

  • Joost van Beusekom
  • Faisal ShafaitEmail author
  • Thomas M. Breuel
Original Paper

Abstract

In large scale document digitization, orientation detection plays an important role, especially in the scenario of digitizing incoming mail. The heavy use of automatic document feeding scanners and moreover automatic processing of facsimiles results in many documents being scanned in the wrong orientation. These misoriented scans have to be corrected, as most subsequent processing steps assume the document to be scanned in the right orientation. Several existing methods for orientation detection use the fact that in Latin script text, ascenders are more likely to occur than descenders. In this paper, we propose a one-step skew and orientation detection method using a well-established geometric text-line model. The advantage of our method is that it combines accurate skew estimation with robust, resolution-independent orientation detection. An interesting aspect of our method is that it incorporates orientation detection into a previously published skew detection method allowing to perform orientation detection, skew estimation, and, if necessary, text-line extraction in one step. The effectiveness of our orientation detection approach is demonstrated on the UW-I dataset, and on publicly available test images from OCRopus. Our method achieves an accuracy of 99% on the UW-I dataset and 100% on test images from OCRopus.

Keywords

Orientation detection Pre-processing Line finding 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vincent, L.: Google book search: document understanding on a massive scale. In: Proceedings of the 9th International Conference on Document Analysis and Recognition, pp. 819–823, Curitiba, Brazil (2007)Google Scholar
  2. 2.
    Shafait F., van Beusekom J., Keysers D., Breuel T.M.: Document cleanup using page frame detection. Int. Jour. Document Anal. Recognit. 11(2), 81–96 (2008)CrossRefGoogle Scholar
  3. 3.
    Shafait, F., Keysers, D., Breuel, T.M.: Efficient implementation of local adaptive thresholding techniques using integral images, In: Proceedings of SPIE Document Recognition and Retrieval XV, vol. 6815, pp. 681510–681510, San Jose, CA, USA (2008)Google Scholar
  4. 4.
    Shafait F., Keysers D., Breuel T.M.: Performance evaluation and benchmarking of six page segmentation algorithms. IEEE Trans. Pattern Anal. Mach. Intel. 30(6), 941–954 (2008)CrossRefGoogle Scholar
  5. 5.
    Smith, R.: An overview of the Tesseract OCR engine, In: Proceedings of the 9th International Conference on Document Analysis and Recognition, pp. 629–633, Curitiba, Brazil, (2007)Google Scholar
  6. 6.
    Breuel, T.M.: The OCRopus open source OCR system, In: Proceedings of SPIE Document Recognition and Retrieval XV, vol. 6815, pp. 0F1–0F15, San Jose, CA, USA, (2008)Google Scholar
  7. 7.
    Cattoni, R., Coianiz, T., Messelodi, S., Modena, C.M.: Geometric layout analysis techniques for document image understanding: a review, Tech. Rep. pp. 9703–9709, IRST, Trento, Italy (1998)Google Scholar
  8. 8.
    Lu Y., Tan C.: A nearest-neighbor chain based approach to skew estimation in document images. Pattern Recognit. Lett. 24(14), 2315–2323 (2003)CrossRefGoogle Scholar
  9. 9.
    Caprari R.S.: Algorithm for text page up/down orientation determination. Pattern Recognit. Lett. 21(4), 311–317 (2001)CrossRefGoogle Scholar
  10. 10.
    Aradhye H.: A generic method for determining up/down orientation of text in roman and non-roman scripts. Pattern Recognit. 38(11), 2114–2131 (2005)CrossRefGoogle Scholar
  11. 11.
    Lu, S., Tan, C.L.: Automatic document orientation detection and categorization through document vectorization, In: Proceedings of the 14th ACM International Conference on Multimedia, pp. 113–116, New York, NY, USA (2006)Google Scholar
  12. 12.
    Le D., Thoma G., Wechsler H.: Automated page orientation and skew angle detection for binary document images. Pattern Recognit. 27(10), 1325–1344 (1994)CrossRefGoogle Scholar
  13. 13.
    Bloomberg, D.S., Kopec, G.E., Dasari, L.: Measuring document image skew and orientation. In: Proceedings of SPIE Document Recognition and Retrieval II, pp. 302–316, San Jose, CA, USA (1995)Google Scholar
  14. 14.
    Phillips, I.T.: User’s reference manual for the UW english/technical document image database III, Tech. rep., Seattle University, Washington (1996)Google Scholar
  15. 15.
    Ávila, B.T., Lins, R.D.: A fast orientation and skew detection algorithm for monochromatic document images, In: Proceedings of the 5th ACM Symposium on Document Engineering, pp. 118–126, New York, NY, USA, (2005)Google Scholar
  16. 16.
    Lu, S., Wang, J., Tan, C.: Fast and accurate detection of document skew and orientation, In: Proceedings of the 9th International Conference on Document Analysis and Recognition, pp. 684–688, Curitiba, Brazil, (2007)Google Scholar
  17. 17.
    Breuel, T.M.: Robust least square baseline finding using a branch and bound algorithm, In: Proceedings of SPIE Document Recognition and Retrieval IX, pp. 20–27, San Jose, CA, USA (2002)Google Scholar
  18. 18.
    Breuel T.M.: A practical, globally optimal algorithm for geometric matching under uncertainty. Electron Notes Theor. Comput. Sci. 46, 1–15 (2001)CrossRefGoogle Scholar
  19. 19.
    Breuel T.M.: Implementation techniques for geometric branch-and-bound matching methods. Comput. Vis. Image Underst. 90(3), 258–294 (2003)zbMATHCrossRefGoogle Scholar
  20. 20.
    Chen, S., Jaisimha, M.Y., Ha, J., Haralick, R.M., Phillips, I.T.: Reference manual for the UW english document image database, Tech. rep., Seattle University, Washington (1993)Google Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  • Joost van Beusekom
    • 1
  • Faisal Shafait
    • 2
    Email author
  • Thomas M. Breuel
    • 1
  1. 1.Department of Computer ScienceTechnische Universität of KaiserslauternKaiserslauternGermany
  2. 2.Image Understanding and Pattern Recognition (IUPR) Research GroupGerman Research Center for Artificial Intelligence (DFKI)KaiserslauternGermany

Personalised recommendations